Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1] 333 117 210 629 187 918  54 237 616 823 646 541   9 618 919 365 180 765 923  99
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1] 823  NA  99 618 919 765 646 365 541  54 180   9 117 629 333 918 616 210  NA 187  NA 923 237
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 4 5 3 1 4 4 1 1 5 3
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "m" "g" "q" "s" "v" "B" "L" "F" "H" "X"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1]  6 15 19
which( manyNumbersWithNA > 900 )
[1]  5 16 22
which( is.na( manyNumbersWithNA ) )
[1]  2 19 21

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 918 919 923
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 918 919 923
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 918 919 923

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "B" "L" "F" "H" "X"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "m" "g" "q" "s" "v"
manyNumbers %in% 300:600
 [1]  TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE  TRUE FALSE FALSE FALSE  TRUE FALSE FALSE
[19] FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  1 12 16
sum( manyNumbers %in% 300:600 )
[1] 3

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] "large" NA      "small" "large" "large" "large" "large" "small" "large" "small" "small" "small" "small" "large"
[15] "small" "large" "large" "small" NA      "small" NA      "large" "small"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "large"   "UNKNOWN" "small"   "large"   "large"   "large"   "large"   "small"   "large"   "small"   "small"  
[12] "small"   "small"   "large"   "small"   "large"   "large"   "small"   "UNKNOWN" "small"   "UNKNOWN" "large"  
[23] "small"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1] 823  NA   0 618 919 765 646   0 541   0   0   0   0 629   0 918 616   0  NA   0  NA 923   0

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 4 5 3 1
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  4  5  3  1
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 22
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 923
which.min( manyNumbersWithNA )
[1] 12
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 9
range( manyNumbersWithNA, na.rm = TRUE )
[1]   9 923

Sorting/ordering of vectors

manyNumbersWithNA
 [1] 823  NA  99 618 919 765 646 365 541  54 180   9 117 629 333 918 616 210  NA 187  NA 923 237
sort( manyNumbersWithNA )
 [1]   9  54  99 117 180 187 210 237 333 365 541 616 618 629 646 765 823 918 919 923
sort( manyNumbersWithNA, na.last = TRUE )
 [1]   9  54  99 117 180 187 210 237 333 365 541 616 618 629 646 765 823 918 919 923  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 923 919 918 823 765 646 629 618 616 541 365 333 237 210 187 180 117  99  54   9  NA  NA  NA
manyNumbersWithNA[1:5]
[1] 823  NA  99 618 919
order( manyNumbersWithNA[1:5] )
[1] 3 4 1 5 2
rank( manyNumbersWithNA[1:5] )
[1] 3 5 1 2 4
sort( mixedLetters )
 [1] "B" "F" "g" "H" "L" "m" "q" "s" "v" "X"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  5.0  7.5  2.0 10.0  2.0  9.0  2.0  5.0  7.5  5.0
rank( manyDuplicates, ties.method = "min" )
 [1]  4  7  1 10  1  9  1  4  7  4
rank( manyDuplicates, ties.method = "random" )
 [1]  4  8  1 10  2  9  3  5  7  6

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.00000000 -0.50000000  0.00000000  0.50000000  1.00000000 -0.63222395 -0.08492404 -1.57677352  1.33507263
[10] -0.66400970 -1.03485318  1.90646008 -0.62232902 -0.94611470  0.67538853
round( v, 0 )
 [1] -1  0  0  0  1 -1  0 -2  1 -1 -1  2 -1 -1  1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0 -0.6 -0.1 -1.6  1.3 -0.7 -1.0  1.9 -0.6 -0.9  0.7
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00 -0.63 -0.08 -1.58  1.34 -0.66 -1.03  1.91 -0.62 -0.95  0.68
floor( v )
 [1] -1 -1  0  0  1 -1 -1 -2  1 -1 -2  1 -1 -1  0
ceiling( v )
 [1] -1  0  0  1  1  0  0 -1  2  0 -1  2  0  0  1

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC